In [1]:
import os
import numpy as np
import pandas as pd
# TensorFlow
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.losses import BinaryCrossentropy, categorical_crossentropy
from tensorflow.keras.utils import plot_model
from tensorflow.keras.optimizers import SGD
# Visualisation libraries
## Text
from colorama import Fore, Back, Style
from IPython.display import Image, display, Markdown, Latex, clear_output
## matplotlib
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
plt.style.use('seaborn-whitegrid')
import matplotlib as mpl
mpl.rcParams['figure.figsize'] = (17, 6)
%matplotlib inline
## seaborn
import seaborn as sns
## plotly
from plotly.offline import init_notebook_mode, iplot
import plotly.graph_objs as go
import plotly.offline as py
from plotly.subplots import make_subplots
import plotly.express as px
import plotly.figure_factory as ff
%config InlineBackend.figure_format = 'retina'
import warnings
warnings.filterwarnings("ignore")
Image Classification¶
This article is based on the TensorFlow Image Classification article where we demonstrate image classification using TensorFlow. The dataset that we use here is a filtered version of Dogs vs Cats dataset from Kaggle.
Dogs vs. Cats Dataset
Downloading Data¶
In [2]:
def Get_Data(_URL, Remove = True):
# The dataset URL
File = _URL.split('/')[-1]
Full_Name = os.path.join(os.getcwd(), File)
# Download the dataset file from the URL
path_to_zip = tf.keras.utils.get_file(fname =Full_Name, origin=_URL, extract=True, cache_dir = os.getcwd())
PATH = os.path.join(os.path.dirname(path_to_zip), 'datasets', File.split('.')[0])
# Deleting the zip file
if Remove:
os.remove(File)
return PATH
#-----------------------------------------------------------------
_URL = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'
PATH = Get_Data(_URL)
Dataset Directory Structure¶
In [3]:
def Path_Tree(PATH):
sep = ' ' * 3
title = PATH.split('\\')[-1]
print(Style.RESET_ALL + Fore.BLUE + Style.NORMAL + '=' * (len(title) +1) + Style.RESET_ALL)
print(Back.BLACK + Fore.CYAN + Style.NORMAL + title+':'+ Style.RESET_ALL)
print(Style.RESET_ALL + Fore.BLUE + Style.NORMAL + '=' * (len(title) +1)+ Style.RESET_ALL)
for entry in os.listdir(PATH):
sub = os.path.join(PATH, entry)
if os.path.isdir(sub):
print('└──',Back.CYAN + Fore.BLACK + Style.NORMAL + entry+':'+ Style.RESET_ALL)
for entry1 in os.listdir(sub):
sub1 = os.path.join(sub, entry1)
if os.path.isdir(sub):
print(sep + '└──',Back.MAGENTA + Fore.BLACK + Style.NORMAL + entry1+':'+ Style.RESET_ALL)
List = os.listdir(sub1)
print(2* sep, Back.YELLOW + Fore.BLACK + Style.NORMAL +
'%i %s files' % (len(List), List[0].split('.')[-1].upper()) + Style.RESET_ALL)
print(2* sep, ', '.join(List[:5]) + ', ...')
#-----------------------------------------------------------------
Path_Tree(PATH)
In [4]:
def Data_Info(PATH):
Set = [];
Subset = [];
Size = [];
DataDirs = {};
for entry in os.listdir(PATH):
sub = os.path.join(PATH, entry)
if os.path.isdir(sub):
DataDirs[entry] = sub
for entry1 in os.listdir(sub):
sub1 = os.path.join(sub, entry1)
if os.path.isdir(sub):
DataDirs[entry + '_' +entry1] = sub1
Set.append(entry.title())
Subset.append(entry1.title())
Size.append(len(os.listdir(sub1)))
DataFrame_Info = pd.DataFrame({'Set': Set, 'Subset': Subset, 'Size':Size})
display(DataFrame_Info.set_index(['Set' , 'Subset']).T)
return DataFrame_Info, DataDirs
#-----------------------------------------------------------------
DataFrame_Info, DataDirs = Data_Info(PATH)
Preprocessing¶
In [5]:
batch_size = 128
epochs = 15
Img_Height = 150
Img_Width = 150
Train Data Image DataGenerator¶
In [6]:
image_gen_train = ImageDataGenerator(
# Rescaling the tensors from values between 0 and 255 to values between 0 and 1
rescale=1./255,
# Applying 45 degrees of rotation randomly
rotation_range=45,
# Range for random horizontal shifts.
width_shift_range=.15,
# Range for random vertical shifts.
height_shift_range=.15,
# applying random horizontal flip augmentation
horizontal_flip=True,
# Applying a zoom augmentation to the dataset to zoom images up to 50%
zoom_range=0.5
)
print(Back.WHITE + Fore.BLACK + Style.NORMAL + 'Train Data:'+ Style.RESET_ALL)
# flow_from_directory method load images from the disk
train_data_gen = image_gen_train.flow_from_directory(batch_size=batch_size,
directory=DataDirs['train'],
shuffle=True,
target_size=(Img_Height, Img_Width),
class_mode='binary')
In [7]:
def plotImages(images_arr, s = 3.4, Title = False):
fig, axes = plt.subplots(1, len(images_arr), figsize=(s* len(images_arr),s))
axes = axes.flatten()
font = FontProperties()
font.set_weight('bold')
for img, ax in zip( images_arr, axes):
ax.imshow(img)
ax.axis('off')
_ = fig.tight_layout()
_ = fig.subplots_adjust(wspace= 5e-3)
if Title:
font = FontProperties()
font.set_weight('bold')
_ = fig.suptitle(Title, y = 1.05, fontsize = 18)
sample_images, _ = next(train_data_gen)
plotImages(sample_images[:4], Title = 'Four Random Pictures from the Train Sample')
augmented_images = [train_data_gen[0][0][0] for i in range(5)]
plotImages(augmented_images, Title = 'Original and Augmented Pictures', s = 3)
Validation Data Image DataGenerator¶
In [8]:
validation_image_generator = ImageDataGenerator(rescale=1./255)
print(Back.WHITE + Fore.BLACK + Style.NORMAL + 'Validation Data:'+ Style.RESET_ALL)
val_data_gen = validation_image_generator.flow_from_directory(batch_size = batch_size,
directory = DataDirs['validation'],
target_size = (Img_Height, Img_Width),
class_mode = 'binary')
sample_images, _ = next(val_data_gen)
plotImages(sample_images[:4], Title = 'Four Random Pictures from the Train Sample')
Modeling¶
We use Keras Sequential model for creating a model.
In [9]:
model = Sequential(name = 'CNN')
model.add(Conv2D(16, 3, padding='same', activation='relu', input_shape=(Img_Height, Img_Width ,3)))
model.add(MaxPooling2D())
# regularization
model.add(Dropout(0.2))
model.add(Conv2D(32, 3, padding='same', activation='relu'))
model.add(MaxPooling2D())
model.add(Conv2D(64, 3, padding='same', activation='relu'))
model.add(MaxPooling2D())
# regularization
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(1))
model.summary()
plot_model(model, show_shapes=True, show_layer_names=False, expand_nested = True, rankdir = 'TB')
Out[9]:
Compiling and fitting the model
In [10]:
model.compile(optimizer = 'adam', loss = BinaryCrossentropy(from_logits=True), metrics = ['accuracy'])
history = model.fit_generator(train_data_gen,
steps_per_epoch = DataFrame_Info.loc[DataFrame_Info['Set'] == 'Train','Size'].sum() // batch_size,
epochs = epochs,
validation_data = val_data_gen,
validation_steps = DataFrame_Info.loc[DataFrame_Info['Set'] == 'Validation','Size'].sum() // batch_size)
clear_output()
In [11]:
def Table_History(history):
Table = pd.DataFrame(pd.DataFrame(history.history).values,
columns = pd.MultiIndex.from_product([['Train', 'Validation'], ['Loss', 'Accuracy']]))
display(Table.style.background_gradient(subset= [('Train', 'Accuracy'), ('Validation', 'Accuracy')], cmap='BuGn')\
.background_gradient(subset= [( 'Train','Loss'), ('Validation', 'Loss')], cmap='Wistia').set_precision(4))
# -------------------------------------------------------------------------------------------
def Plot_History(history, L = [0, 1], R = [0, 1]):
fig = make_subplots(rows=1, cols=2, horizontal_spacing = 0.05, column_widths=[0.5, 0.5],
specs=[[{"type": "scatter"},{"type": "scatter"}]],
subplot_titles=('Loss', 'Accuracy'))
Temp = pd.DataFrame(history.history)
IT = np.arange(1, Temp.index.max()+2)
fig.add_trace(go.Scatter(x= IT,
y= Temp['loss'].values,
line=dict(color='DeepPink', width= 1.5), name = 'Train'), 1, 1)
fig.add_trace(go.Scatter(x= IT,
y= Temp['val_loss'].values,
line=dict(color='MidnightBlue', width= 1.5), name = 'Validation'), 1, 1)
fig.update_traces(showlegend = False, row=1, col=1)
fig.add_trace(go.Scatter(x= IT,
y= Temp['accuracy'].values,
line=dict(color='DeepPink', width= 1.5), name = 'Train'), 1, 2)
fig.add_trace(go.Scatter(x= IT,
y= Temp['val_accuracy'].values,
line=dict(color='MidnightBlue', width= 1.5), name = 'Validation'), 1, 2)
fig.update_layout(plot_bgcolor= 'white')
fig.update_xaxes(range=[IT.min()-1, IT.max()+1],
zeroline=True, zerolinewidth=1, zerolinecolor='Lightgray',
showline=True, linewidth=1, linecolor='Lightgray', mirror=True, row=1, col=1)
fig.update_yaxes(range=L,
showgrid=True, gridwidth=1, gridcolor='Lightgray',
zeroline=True, zerolinewidth=1, zerolinecolor='Lightgray',
showline=True, linewidth=1, linecolor='Lightgray', mirror=True, row=1, col=1)
fig.update_xaxes(range=[IT.min()-1, IT.max()+1],
zeroline=True, zerolinewidth=1, zerolinecolor='Lightgray',
showline=True, linewidth=1, linecolor='Lightgray', mirror=True, row=1, col=2)
fig.update_yaxes(range=R,
showgrid=True, gridwidth=1, gridcolor='Lightgray',
zeroline=True, zerolinewidth=1, zerolinecolor='Lightgray',
showline=True, linewidth=1, linecolor='Lightgray', mirror=True, row=1, col=2)
fig.show()
# -------------------------------------------------------------------------------------------
In [12]:
Table_History(history)
Plot_History(history, L = [0.5, 1], R = [0.4, .8])
References¶
- TensorFlow Image, https://www.tensorflow.org/api_docs/python/tf/image
- Image classification, https://www.tensorflow.org/tutorials/images/classification
- Dogs vs. Cats, https://www.kaggle.com/c/dogs-vs-cats/data